Bishal Gurung

A simple spectrophotometric method for estimating total glucosinolates in mustard de-oiled cake

ABSTRACT Glucosinolates are anti-nutritional factors present abundantly in the seed meal fraction of oilseed Brassica species. They are found in varying levels among different genotypes. Those genotypes containing less than 30 µmol/g are considered low/zero glucosinolate type and are preferred for edible purposes due to low pungency. Twenty two different genotypes were taken for the analysis of glucosinolates by spectrophotometry. A regression model was obtained using Ordinary Least Square technique which predicted a formula. Total glucosinolates (µmol/g) = 1.40 + 118.86 × A425, where A425 is the absorbance at 425 nm. The total glucosinolate content obtained by the prediction formula when compared with HPLC data showed a correlation coefficient of 0.942. This high correlation between the two data sets validated the developed methodology. This method also simplifies the estimation of total glucosinolates by excluding the use of HPLC or other sophisticated instruments.

Monte Carlo simulation for comparison of different estimators of long memory parameter: An application of ARFIMA model for forecasting commodity price

Time series with long memory or long-range dependence occurs frequently in agricultural commodity prices. For de- scribing long memory, fractional integration is considered. The autoregressive fractionally integrated moving-average (ARFIMA) model along with its different estimation procedures is investigated. For the present investigation, the daily spot prices of mustard in Mumbai market are used. Autocorrelation (ACF) and partial autocorrelation (PACF) functions showed a slow hyperbolic decay indicating the presence of long memory. On the basis of minimum AIC values, the best model is identified for each series. Eval- uation of forecasting is carried out with root mean squares prediction error (RMSPE), mean absolute prediction error (MAPE) and relative mean absolute prediction error (RMAPE). The residuals of the fitted models were used for diagnostic checking. Long memory parameter of ARFIMA model is computed by Geweke and Porter-Hudak (GPH), Gaussian semiparametric and wavelet method by using Maximal overlap discrete wavelet transform (MODWT). To this end, a comparison in the performance of different estimation procedures is carried out by Monte Carlo simulation technique. The R software package has been used for data analysis.

Kalman filter-based modelling and forecasting of stochastic volatility with threshold

We propose a parametric nonlinear time-series model, namely the Autoregressive-Stochastic volatility with threshold (AR-SVT) model with mean equation for forecasting level and volatility. Methodology for estimation of parameters of this model is developed by first obtaining recursive Kalman filter time-update equation and then employing the unrestricted quasi-maximum likelihood method. Furthermore, optimal one-step and two-step-ahead out-of-sample forecasts formulae along with forecast error variances are derived analytically by recursive use of conditional expectation and variance. As an illustration, volatile all-India monthly spices export during the period January 2006 to January 2012 is considered. Entire data analysis is carried out using EViews and matrix laboratory (MATLAB) software packages. The AR-SVT model is fitted and interval forecasts for 10 hold-out data points are obtained. Superiority of this model for describing and forecasting over other competing models for volatility, namely AR-Generalized autoregressive conditional heteroscedastic, AR-Exponential GARCH, AR-Threshold GARCH, and AR-Stochastic volatility models is shown for the data under consideration. Finally, for the AR-SVT model, optimal out-of-sample forecasts along with forecasts of one-step-ahead variances are obtained.

An insight into technology diffusion of tractor through Weibull growth model

ABSTRACT Most of the technological innovation diffusion follows an S-shaped curve. But, in many practical situations this may not hold true. To this end, Weibull model was proposed to capture the diffusion of new technological innovation, which does not follow any specific pattern. Nonlinear growth models play a very important role in getting an insight into the underlying mechanism. These models are generally ‘mechanistic’ as the parameters have meaningful interpretation. The nonlinear method of estimation of parameters of Weibull model fails to converge. Taking this problem into consideration, we propose the use of a powerful technique of genetic algorithm for parameter estimation. The methodology is also validated by simulation study to check whether parameter estimates are closer to the real value. For illustration purpose, we model the tractor density time-series data of India as a whole and some major states of India. It is seen that fitted Weibull model is able to capture the technology diffusion process in a reasonable manner. Further, comparison is also made with Logistic and Gompertz model; and is found to perform better for the data sets under consideration.

An alternative method for forecasting price volatility by combining models

ABSTRACT In this article, we study the volatility in the monthly price series of edible oils in domestic and international markets using the two popular family of nonlinear time-series models, viz, Generalized autoregressive conditional heteroscedastic (GARCH) models and Stochastic volatility (SV) models. To improve the forecasts of the volatility process, we also propose a new method of combining the volatility of these two competing models using the powerful technique of Kalman filter. The individual models as well as the combined models are assessed on their ability to predict the correct directional change (CDC) in future values as well as other goodness-of-fit statistics. Further, forecasting performance are also evaluated by computing various measures to validate the proposed methodology.

Modeling Long Memory in Volatility for Spot Price of Lentil with Multi-step Ahead Out-of-sample Forecast Using AR-FIGARCH Model

The potential presence of long memory (LM) properties in return and volatility of the spot price of lentil in Indore market has been investigated. Geweke and Porter-Hudak (1983) (GPH) method has been applied to test for presence of long range dependence in the volatility processes for the series. Stationarity of the series has been tested using Augmented Dickey-Fuller (ADF) unit root test and Philips-Peron (PP) unit root test. It is observed that both the log returns as well as squared log returns series are stationary at level but there is a significant presence of long memory in squared log return series. Accordingly, AR-FIGARCH model was applied for forecasting the volatility of lentil price. To this end, window based evaluation of forecasting is carried out with the help of Mean squares prediction error (MSPE), Root MSPE (RMSPE), Mean absolute prediction error (MAPE) and Relative MAPE (RMAPE). The residuals of the fitted models were used for diagnostic checking. Out-of sample forecast of volatility has been computed for 1st June-31st July, 2015 along with the percentage deviation from the actual price. The maximum deviation has been found to be 2.55%. The R software package has been used for data analysis.

Stability Analysis of Indian Spices Export – A Markov Chain Approach

Spices are an important horticultural crop of India as it adds substantially to the agriculture GDP. It has been seen that there is high fluctuations in the export of spices to other countries. To, this end, we employ the concept of Markov chain (MC) to analyze the dynamics of spices export to different countries of the world. It was observed that the countries which were stable destination for Indian spices export were Canada for black pepper, UK for chilli, Bangladesh for turmeric, UAE for cumin and Malaysia for coriander. The transitional probability matrix obtained using MC indicated that most of the traditional importers have shown low retention probability which may be due to tough competition arising in spices trade and trade related barriers in the developed nations. So, policies may be framed by planners for export towards these countries. Though in most of the spices, India has managed to retain one of its original markets, but it should not have high dependency on one market alone to avoid trade risk in the long-run. New markets also need to be explored and more stress has to be given to the traditional buyers for maintaining present status of export and market share in future.

Stochastic Model for Sticklac Forecasting in India

In the present study, we aim to devise most appropriate prediction model for Indias annual sticklac production data based on Exponential Autoregressive (EXPAR) model. Statistical modelling and forecasting of agricultural time-series data plays a vital role in comprehending the underlying relationships among statistically significant variables and helping the planners in policy making. Accordingly, in this paper, a promising methodology of EXPAR family of models has been employed to describe Indias annual sticklac production data that depict such cyclical fluctuations. The fitted EXPAR model captured the data in a satisfactory manner. Further, the performance of the model is compared by computing various measures of goodness-of-fit and forecast performance. We conclude that EXPAR model performs quite well for modelling as well as forecasting of the cyclical data under consideration.